Presentation is loading. Please wait.

Presentation is loading. Please wait.

Grouping and Segmentation Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/01/10.

Similar presentations


Presentation on theme: "Grouping and Segmentation Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/01/10."— Presentation transcript:

1 Grouping and Segmentation Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/01/10

2 Last week EM Mixture of Gaussians Segmentation using EM and graph cuts

3 Today’s class Segmentation and grouping – Gestalt cues – By clustering (mean-shift) – By boundaries (watershed)

4 Gestalt grouping

5

6 German: Gestalt - "form" or "whole” Berlin School, early 20th century Kurt Koffka, Max Wertheimer, and Wolfgang Köhler View of brain: whole is more than the sum of its parts holistic parallel analog self-organizing tendencies Slide from S. Saverese Gestalt psychology or gestaltism

7 The Muller-Lyer illusion Gestaltism

8 We perceive the interpretation, not the senses

9 Principles of perceptual organization From Steve Lehar: The Constructive Aspect of Visual Perception

10 Principles of perceptual organization

11 Gestaltists do not believe in coincidence

12 Emergence

13 From Steve Lehar: The Constructive Aspect of Visual Perception Grouping by invisible completion

14 From Steve Lehar: The Constructive Aspect of Visual Perception Grouping involves global interpretation

15 From Steve Lehar: The Constructive Aspect of Visual Perception

16 Gestalt cues Good intuition and basic principles for grouping Basis for many ideas in segmentation and occlusion reasoning Some (e.g., symmetry) are difficult to implement in practice

17 Moving on to image segmentation … Goal: Break up the image into meaningful or perceptually similar regions

18 Segmentation for feature support 50x50 Patch

19 Segmentation for efficiency [Felzenszwalb and Huttenlocher 2004] [Hoiem et al. 2005, Mori 2005] [Shi and Malik 2001]

20 Segmentation as a result Rother et al. 2004

21 Types of segmentations OversegmentationUndersegmentation Multiple Segmentations

22 Major processes for segmentation Bottom-up: group tokens with similar features Top-down: group tokens that likely belong to the same object [Levin and Weiss 2006]

23 Segmentation using clustering Kmeans Mean-shift

24 Source: K. Grauman Feature Space

25 Image Clusters on intensityClusters on color K-means clustering using intensity alone and color alone

26 K-Means pros and cons Pros – Simple and fast – Easy to implement Cons – Need to choose K – Sensitive to outliers Usage – Rarely used for pixel segmentation

27 Versatile technique for clustering-based segmentation D. Comaniciu and P. Meer, Mean Shift: A Robust Approach toward Feature Space Analysis, PAMI 2002. Mean shift segmentation

28 Mean shift algorithm Try to find modes of this non-parametric density

29 Kernel density estimation Kernel density estimation function Gaussian kernel

30 Region of interest Center of mass Mean Shift vector Slide by Y. Ukrainitz & B. Sarel Mean shift

31 Region of interest Center of mass Mean Shift vector Slide by Y. Ukrainitz & B. Sarel Mean shift

32 Region of interest Center of mass Mean Shift vector Slide by Y. Ukrainitz & B. Sarel Mean shift

33 Region of interest Center of mass Mean Shift vector Mean shift Slide by Y. Ukrainitz & B. Sarel

34 Region of interest Center of mass Mean Shift vector Slide by Y. Ukrainitz & B. Sarel Mean shift

35 Region of interest Center of mass Mean Shift vector Slide by Y. Ukrainitz & B. Sarel Mean shift

36 Region of interest Center of mass Slide by Y. Ukrainitz & B. Sarel Mean shift

37 Simple Mean Shift procedure: Compute mean shift vector Translate the Kernel window by m(x) Computing the Mean Shift Slide by Y. Ukrainitz & B. Sarel

38 Real Modality Analysis

39 Attraction basin: the region for which all trajectories lead to the same mode Cluster: all data points in the attraction basin of a mode Slide by Y. Ukrainitz & B. Sarel Attraction basin

40

41 Mean shift clustering The mean shift algorithm seeks modes of the given set of points 1.Choose kernel and bandwidth 2.For each point: a)Center a window on that point b)Compute the mean of the data in the search window c)Center the search window at the new mean location d)Repeat (b,c) until convergence 3.Assign points that lead to nearby modes to the same cluster

42 Compute features for each pixel (color, gradients, texture, etc) Set kernel size for features K f and position K s Initialize windows at individual pixel locations Perform mean shift for each window until convergence Merge windows that are within width of K f and K s Segmentation by Mean Shift

43 http://www.caip.rutgers.edu/~comanici/MSPAMI/msPamiResults.html Mean shift segmentation results

44 http://www.caip.rutgers.edu/~comanici/MSPAMI/msPamiResults.html

45 Mean-shift: other issues Speedups – Binned estimation – Fast search of neighbors – Update each window in each iteration (faster convergence) Other tricks – Use kNN to determine window sizes adaptively Lots of theoretical support D. Comaniciu and P. Meer, Mean Shift: A Robust Approach toward Feature Space Analysis, PAMI 2002.

46 Mean shift pros and cons Pros – Good general-practice segmentation – Flexible in number and shape of regions – Robust to outliers Cons – Have to choose kernel size in advance – Not suitable for high-dimensional features When to use it – Oversegmentatoin – Multiple segmentations – Tracking, clustering, filtering applications

47 Watershed algorithm

48 Watershed segmentation ImageGradient Watershed boundaries

49 Meyer’s watershed segmentation 1.Choose local minima as region seeds 2.Add neighbors to priority queue, sorted by value 3.Take top priority pixel from queue 1.If all labeled neighbors have same label, assign to pixel 2.Add all non-marked neighbors 4.Repeat step 3 until finished Meyer 1991 Matlab: seg = watershed(bnd_im)

50 Simple trick Use Gaussian or median filter to reduce number of regions

51 Watershed usage Use as a starting point for hierarchical segmentation – Ultrametric contour map (Arbelaez 2006) Works with any soft boundaries – Pb – Canny – Etc.

52 Watershed pros and cons Pros – Fast (< 1 sec for 512x512 image) – Among best methods for hierarchical segmentation Cons – Only as good as the soft boundaries – Not easy to get variety of regions for multiple segmentations – No top-down information Usage – Preferred algorithm for hierarchical segmentation

53 Things to remember Gestalt cues and principles of organization Uses of segmentation – Efficiency – Better features – Want the segmented object Mean-shift segmentation – Good general-purpose segmentation method – Generally useful clustering, tracking technique Watershed segmentation – Good for hierarchical segmentation – Use in combination with boundary prediction

54 Further reading Nicely written mean-shift explanation (with math) http://saravananthirumuruganathan.wordpress.com/2010/04/01/introduction-to-mean-shift-algorithm/ Mean-shift paper by Comaniciu and Meer http://www.caip.rutgers.edu/~comanici/Papers/MsRobustApproach.pdf Adaptive mean shift in higher dimensions http://mis.hevra.haifa.ac.il/~ishimshoni/papers/chap9.pdf Contours to regions (watershed): Arbelaez et al. 2009 http://www.eecs.berkeley.edu/~arbelaez/publications/Arbelaez_Maire_Fowlkes_Malik_CVPR2009.pdf

55 Recap of Grouping and Fitting

56 Edge and line detection Canny edge detector = smooth  derivative  thin  threshold  link Generalized Hough transform = points vote for shape parameters Straight line detector = canny + gradient orientations  orientation binning  linking  check for straightness

57 Robust fitting and registration Key algorithms RANSAC, Hough Transform

58 Clustering Key algorithm K-means

59 EM and Mixture of Gaussians Tutorials: http://www.cs.duke.edu/courses/spring04/cps196.1/.../EM/tomasiEM.pdf http://www-clmc.usc.edu/~adsouza/notes/mix_gauss.pdf http://www.cs.duke.edu/courses/spring04/cps196.1/.../EM/tomasiEM.pdf http://www-clmc.usc.edu/~adsouza/notes/mix_gauss.pdf

60 Segmentation Mean-shift segmentation – Flexible clustering method, good segmentation Watershed segmentation – Hierarchical segmentation from soft boundaries Normalized cuts – Produces regular regions – Slow but good for oversegmentation MRFs with Graph Cut – Incorporates foreground/background/object model and prefers to cut at image boundaries – Good for interactive segmentation or recognition

61 Next section: Recognition How to recognize – Specific object instances – Faces – Scenes – Object categories


Download ppt "Grouping and Segmentation Computer Vision CS 543 / ECE 549 University of Illinois Derek Hoiem 03/01/10."

Similar presentations


Ads by Google